torch.Tensor の操作

>>> a = torch.Tensor((1,2))
>>> a.shape
torch.Size([2])
>>> a[:,None].shape 
torch.Size([2, 1])
>>> a.reshape((1,-1)).shape
torch.Size([1, 2])

>>> import torch
>>> a = torch.Tensor((1,2))
>>> b = torch.Tensor((3,2))
>>> a*b
tensor([3., 4.])
>>> a/b
tensor([0.3333, 1.0000])
>>> a==b
tensor([False,  True])
>>> a==1
tensor([ True, False])
>>> c = torch.Tensor((3,2,1)) 
>>> a==c
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
RuntimeError: The size of tensor a (2) must match the size of tensor b (3) at non-singleton dimension 0

>>> a = torch.Tensor((1,2))
>>> print("yes" if a else "no")
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
RuntimeError: Boolean value of Tensor with more than one value is ambiguous
>>> a.all()
tensor(False)
>>> a.any()
tensor(True)